检索结果-内蒙古大学图书馆

Enforcing connectivity of 3D linear structures using their 2D projections

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Oner, Doruk Osman, Hussein Kozinski, Mateusz Fua, Pascal Computer Vision Laboratory École Polytechnique Fédérale de Lausanne Switzerland Institute of Computer Graphics and Vision Graz University of Technology Austria

Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not capture the topological properties of these structures. As a result, the connectivity of the recovered structures is often wrong, which lessens their usefulness. In this paper, we propose to improve the 3D connectivity of our results by minimizing a sum of topology-aware losses on their 2D projections. This suffices to increase the accuracy and to reduce the annotation effort required to provide the required annotated training data. Code is available at https://***/doruk-oner/ConnectivityOnProjections. Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

学校读者我要写书评

暂无评论

Sit Back and Relax: Learning to Drive Incrementally in All W...

IEEE Symposium on Intelligent Vehicle

作者： Stefan Leitner M. Jehanzeb Mirza Wei Lin Jakub Micorek Marc Masana Mateusz Kozinski Horst Possegger Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Christian Doppler Laboratory for Semantic 3D Computer Vision Silicon Austria Labs TU Graz - SAL Dependable Embedded Systems Lab

In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. However, their performance deteriorates significantly when tested in degrading weather conditions. In addition, even when adapted to perform robustly in a sequence of different weather conditions, they are often unable to perform well in all of them and suffer from catastrophic forgetting. To efficiently mitigate forgetting, we propose Domain-Incremental Learning through Activation Matching (DILAM), which employs unsupervised feature alignment to adapt only the affine parameters of a clear weather pre-trained network to different weather conditions. We propose to store these affine parameters as a memory bank for each weather condition and plug-in their weather-specific parameters during driving (i.e. test time) when the respective weather conditions are encountered. Our memory bank is extremely lightweight, since affine parameters account for less than 2% of a typical object detector. Furthermore, contrary to previous domain-incremental learning approaches, we do not require the weather label when testing and propose to automatically infer the weather condition by a majority voting linear classifier.

关键词：

vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fruhwirth-Reisinger, Christian Lin, Wei Malić, Dušan Bischof, Horst Possegger, Horst Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria Institute for Machine Learning Johannes Kepler University Linz Austria

Accurate 3D object detection in LiDAR point clouds is crucial for autonomous driving systems. To achieve state-of-the-art performance, the supervised training of detectors requires large amounts of human-annotated data, which is expensive to obtain and restricted to predefined object categories. To mitigate manual labeling efforts, recent unsupervised object detection approaches generate class-agnostic pseudo-labels for moving objects, subsequently serving as supervision signal to bootstrap a detector. Despite promising results, these approaches do not provide class labels or generalize well to static objects. Furthermore, they are mostly restricted to data containing multiple drives from the same scene or images from a precisely calibrated and synchronized camera setup. To overcome these limitations, we propose a vision-language-guided unsupervised 3D detection approach that operates exclusively on LiDAR point clouds. We transfer CLIP knowledge to classify point clusters of static and moving objects, which we discover by exploiting the inherent spatio-temporal information of LiDAR point clouds for clustering, tracking, as well as box and label refinement. Our approach outperforms state-of-the-art unsupervised 3D object detectors on the Waymo Open Dataset (+23 AP3D) and Argoverse 2 (+7.9 AP3D) and provides class labels not solely based on object size assumptions, marking a significant advancement in the field. Code will be available at https://***/chreisinger/ViLGOD. © 2024, CC BY-NC-SA.

关键词： Visual languages

Enhanced Data Augmentation Using Synthetic Data for Brain Tumour Segmentation 1

学校读者我要写书评

暂无评论

Challenge on Brain Tumor Segmentation, BraTS 2023, International Challenge on Cross-Modality Domain Adaptation for Medical Image Segmentation, CrossMoDA 2023, held in conjunction with the Medical Image Computing for computer Assisted Intervention Conference, MICCAI 2023

作者： Ferreira, André Solak, Naida Li, Jianning Dammann, Philipp Kleesiek, Jens Alves, Victor Egger, Jan Center Algoritmi/LASI University of Minho Braga4710-057 Portugal Computer Algorithms for Medicine Laboratory Graz Austria University Medicine Essen Girardetstraße 2 Essen45131 Germany University Medicine Essen Hufelandstraße 55 Essen45147 Germany Partner Site Essen Hufelandstraße 55 Essen45147 Germany Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16 Graz8010 Austria Department of Neurosurgery and Spine Surgery University Hospital Essen Essen Germany

ISBN: (数字)9783031761638

ISBN: (纸本)9783031761621

Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for adult glioma segmentation, the Task 1 of the BraTS 2023 challenge. The first model is the standard nnU-Net, the second is the Swin UNETR and the third is the winning solution of the BraTS 2021 Challenge. The entire pipeline is built on the nnU-Net implementation, except for the generation of the synthetic data. The use of convolutional algorithms and transformers is able to fill each other’s knowledge gaps. Our solution achieves the lesion-wise Dice metric of 0.8851, 0.8719, 0.8685 and lesion-wise HD95 of 22.838, 22.974, 16.713 (whole tumour, tumour core and enhancing tumour) on the testing cohort. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Generative adversarial networks

DRT: Detection Refinement for Multiple Object Tracking 32

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking

32nd British Machine vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Leitner, Stefan Mirza, M. Jehanzeb Lin, Wei Micorek, Jakub Masana, Marc Kozinski, Mateusz Possegger, Horst Bischof, Horst Institute for Computer Graphics and Vision Graz University of Technology Austria Christian Doppler Laboratory for Embedded Machine Learning Austria Christian Doppler Laboratory for Semantic 3D Computer Vision Austria TU Graz SAL Dependable Embedded Systems Lab Silicon Austria Labs Austria

关键词： Object detection

EC-SfM: Efficient Covisibility-based Structure-from-Motion for Both Sequential and Unordered Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Zhichao Bao, Chong Zhou, Xin Liu, Haomin Bao, Hujun Zhang, Guofeng State Key Laboratory of Computer Aided Design and Computer Graphics Zhejiang University Hangzhou310058 China SenseTime Research Hangzhou311215 China ZJU-SenseTime Joint Lab of 3D Vision China

Structure-from-Motion is a technology used to obtain scene structure through image collection, which is a fundamental problem in computer vision. For unordered Internet images, SfM is very slow due to the lack of prior knowledge about image overlap. For sequential images, knowing the large overlap between adjacent frames, SfM can adopt a variety of acceleration strategies, which are only applicable to sequential data. To further improve the reconstruction efficiency and break the gap of strategies between these two kinds of data, this paper presents an efficient covisibility-based incremental SfM. Different from previous methods, we exploit covisibility and registration dependency to describe the image connection which is suitable to any kind of data. Based on this general image connection, we propose a unified framework to efficiently reconstruct sequential images, unordered images, and the mixture of these two. Experiments on the unordered images and mixed data verify the effectiveness of the proposed method, which is three times faster than the state-of-the-art on feature matching, and an order of magnitude faster on reconstruction without sacrificing the accuracy. The source code is publicly available at https://***/openxrlab/xrsfm. © 2023, CC BY.

关键词： HTTP

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mirza, M. Jehanzeb Karlinsky, Leonid Lin, Wei Kozinski, Mateusz Possegger, Horst Feris, Rogerio Bischof, Horst Institute of Computer Graphics and Vision TU Graz Austria Christian Doppler Laboratory for Embedded Machine Learning Austria MIT-IBM Watson AI Lab United States

Recently, large-scale pre-trained vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language prompts. However, despite these great advances, the performance of these zero-shot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine-tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories. Using our label-free approach, we are able to attain significant performance improvements over the zero-shot performance of the base VL model and other contemporary methods and baselines on a wide variety of datasets, demonstrating absolute improvement of up to 11.7% (3.8% on average) in the label-free setting. Moreover, despite our approach being label-free, we observe 1.3% average gains over leading few-shot prompting baselines that do use 5-shot supervision. © 2023, CC BY.

关键词： Image classification

Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Oner, Doruk Kozinski, Mateusz Citraro, Lenoardo Fua, Pascal The Computer Vision Laboratory EPFL Switzerland The Institute of Computer Vision and Graphics TU Graz Austria

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data is often hard to interpret visually and in part because the 3D interfaces are awkward to use. In this paper, we introduce a method that explicitly accounts for annotation inaccuracies. To this end, we treat the annotations as active contour models that can deform themselves while preserving their topology. This enables us to jointly train the network and correct potential errors in the original annotations. The result is an approach that boosts performance of deep networks trained with potentially inaccurate annotations. Code has been released at https://***/dorukoner/AdjustingAnnotationswithSnakes. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning